Intelligent Caching Strategies for 5G Edge Networks using Machine Learning

To reduce latency and improve the user experience, content caching solutions at the network periphery will become increasingly important as 5G networks and data-intensive applications. In this proposed work, the deployment of a caching architecture for 5G periphery networks using machine learning is done. Utilizing information on user behavior, network conditions, and content prominence enables more accurate forecasts and cache management decisions. This trains the prediction models using a wide range of machine-learning techniques to accommodate the ever-changing needs of both networks and content. To evaluate the efficiency of the proposed architecture by measuring its ability to increase cache hit rates and decrease latency. These techniques significantly outperform the standard caching methods. With the intelligent caching architecture of 5G periphery networks, throughput is increased, latency is reduced, and congestion is alleviated. The findings of this study contribute to the growing corpus of literature on AI-driven optimization in 5G networks and shed light on how such solutions could be enhanced for future networks. Neural Networks achieved 96% accuracy than SVM which is 93%.